近年來，迷因(meme)在全球迅速流行，尤其在2019-2022年COVID-19疫情期間，其創作與使用量大幅增加，帶動相關研究的發展。然而，迷因的相關研究常因其特性而面臨挑戰，如資料量龐大、匿名性以及多模態等特質。由於這個因素，本研究旨在提出一套的資料分析方法，用於協助迷因現象的研究者分析大量且複雜的迷因圖片。本研究從視覺和語意兩種角度來進行迷因圖片的分析，並結合機器學習與人工智慧的相關技術，開發一套名為「迷因現象之視覺及語意模式探勘系統」（簡稱MEME-PAM）的分析系統。
本研究蒐集Twitter上的2955張迷因圖片作為迷因現象實驗資料集。本研究藉由表徵評估實驗來挑選出適合用於擷取迷因圖片的視覺表徵及語意表徵之深度學習模型，針對從實驗資料集中選出兩種主題的200張迷因圖片進行分群，最後得到出ConvNeXtLarge視覺表徵深度學習模型，及all-MiniLM-L12-v2語意表徵深度學習模型。本研究利用分群驗證實驗分別計算出2955張迷因圖片的視覺模式及語意模式最佳分群數量，最後得到視覺模式49種及語意模式46種。本研究透過該兩項實驗成功從迷因圖片中擷取視覺表徵及語意表徵，並且使MEME-PAM具備分群驗證的準確性下將迷因現象區成多種模式。
本研究最後利用前實驗研究法進行專家評估實驗，邀請共五位專家評估MEME-PAM所探勘出的視覺模式及語意模式的有效性。實驗結果得出MEME-PAM所探勘出的視覺模式的有效性普遍受到專家肯定，而語意模式則因受限於短文本及缺乏先備知識情況下是難以解讀。

In recent years, the global popularity of "memes" has surged, particularly during the COVID-19 pandemic from 2019 to 2022, leading to a marked increase in their creation and use, which has spurred the growth of related research. However, research on memes often faces challenges due to their characteristics due to their characteristics such as: the large volume of data, anonymity, and multimodality. To address this, this study aims to propose a data analysis methodology to assist researchers in analyzing the large volume and complexity of meme images. This study analyzes meme images from visual and semantic perspectives, and develops a system called "Meme Visual and Semantic Pattern Mining System" (MEME-PAM) by combining machine learning and artificial intelligence techniques. As a result, 2955 memes on Twitter were collected as an experimental dataset for the meme analysis. A representation evaluation experiment was conducted to select deep learning models suitable for the visual and semantic representation of memes. A total of 200 memes from two themes were selected from the experimental dataset, leading to the selection of the ConvNeXtLarge model for visual representation and the all-MiniLM-L12-v2 model for semantic representation. In this study, the optimal numbers of visual patterns and semantic patterns for 2,955 memes were calculated through clustering verification experiments, resulting in 49 visual patterns and 46 semantic patterns. Through these two experiments enabling MEME-PAM to distinguish meme phenomena into multiple patterns with verified clustering accuracy. At the end of this study, five experts were invited to evaluate the effectiveness of the visual and semantic patterns discovered by MEME-PAM. The experimental results show that the effectiveness of the visual patterns explored by MEME-PAM is generally recognized by experts, while the semantic patterns are difficult to interpret due to the limitations of short text and lack of prior knowledge.

目次
第一章 緒論　　　1
第一節 研究背景與動機　　　1
第二節 研究目的　　　3
第三節 研究問題　　　4
第四節 名詞解釋　　　4
一、迷因現象(meme phenomena)　　　4
二、視覺表徵(visual representation)與語意表徵(semantic representation)　　　5
三、視覺模式(visual pattern)與語意模式(semantic pattern)　　　5
第二章 文獻探討　　　7
第一節 迷因現象　　　7
第二節 深度學習之視覺表徵與語意表徵　　　10
第三節 非監督式學習技術之分群　　　12
第三章 迷因現象之視覺及語意模式探勘系統　　　17
第一節 系統設計　　　17
第二節 系統架構　　　18
一、資料儲存模組　　　19
二、表徵擷取模組　　　19
三、自動化模式探勘模組　　　19
四、模式探索模組　　　20
第三節 系統開發與運作環境　　　20
一、程式語言　　　20
二、系統開發工具　　　21
三、開發環境　　　21
第四節 視覺表徵擷取處理流程　　　22
一、文字模糊化　　　22
二、自動裁切　　　22
三、視覺表徵擷取　　　24
第五節 語意表徵擷取處理流程　　　25
一、光學字元識別　　　25
二、語意表徵擷取　　　27
第六節 自動化模式探勘模組　　　27
一、K 平均法　　　28
二、分群驗證　　　28
三、代表程度排序　　　29
四、分群視覺化　　　29
第七節 模式探索模組　　　30
一、分群結果頁面　　　31
二、模式列表頁面　　　33
三、單一模式頁面　　　34
四、原始貼文頁面　　　36
第四章 研究設計與實施　　　37
第一節 研究目的與問題　　　37
第二節 表徵評估實驗設計　　　38
一、表徵評估實驗設計與流程　　　38
二、視覺表徵深度學習模型評估實驗設計　　　39
三、語意表徵深度學習模型評估實驗設計　　　42
第三節 分群驗證實驗設計　　　45
第四節 專家評估實驗設計　　　46
一、專家評估實驗參與者抽樣　　　48
二、第一階段：實驗前說明　　　48
三、第二階段：迷因現象視覺模式評估　　　48
四、第三階段：迷因現象語意模式評估　　　49
五、專家評估實驗環境　　　50
第五節 研究工具　　　50
一、迷因現象之視覺及語意模式探勘系統(MEME-PAM)　　　51
二、迷因現象實驗資料集　　　51
三、研究參與知情同意書　　　51
四、模式評估訪談大綱　　　51
第六節 研究範圍與限制　　　57
一、迷因現象來源社群的抽樣限制　　　57
二、迷因現象時間範圍的抽樣限制　　　57
三、迷因現象資料類型的分析限制　　　58
第五章 研究結果與分析　　　59
第一節 表徵評估實驗結果　　　59
一、視覺表徵深度學習模型評估實驗結果　　　59
二、語意表徵深度學習模型評估實驗結果　　　60
三、表徵評估實驗結果小結ｖ61
第二節 分群驗證實驗結果　　　61
二、視覺模式分群驗證實驗結果　　　62
二、語意模式分群驗證實驗結果　　　65
三、分群評估實驗結果小結　　　68
第三節 專家評估實驗結果　　　69
一、專家評估實驗參與者簡介　　　69
二、視覺模式有效性之專家評估結果　　　69
三、語意模式有效性之專家評估結果　　　79
四、專家評估實驗結果之討論　　　91
第六章 結論與建議　　　95
第一節 結論　　　95
一、MEME-PAM 能擷取迷因圖片視覺表徵與語意表徵，且視覺表徵可區別出不同主題　　　95
二、MEME-PAM 所探勘出視覺模式與語意模式具備分群驗證的準確性，且呈現出多元主題的迷因現象　96
三、視覺模式的有效性普遍受到專家肯定，加入脈絡資訊進一步改善　　　96
四、專家認為語意模式不易解讀，因受限於短文本限制和缺乏先備知識支援　　　97
第二節 研究建議　　　97
一、增添研究者能夠命名與註記的功能　　　97
二、增加脈絡資訊來助於解讀迷因現象　　　98
三、搭配生成式人工智慧來輔助解讀迷因現象　　　98
四、專家分群結果與系統探勘結果的比較　　　99
第三節 未來研究方向　　　99
一、結合視覺及語意兩種角度來深入分析迷因現象　　　99
二、使用特定特徵的視覺表徵或語意表徵分析迷因現象　　　99
三、擴展MEME-PAM 在迷因現象研究的應用　　　100
參考文獻　　　101
附錄一 研究參與知情同意書　　　111

表次
表4-1 視覺表徵評估之候選模型的模型大小、Top-1 準確率及參數大小比較　　　40
表4-2 語意表徵評估候選模型的句子語意向量評估分數　　　44
表4-3 視覺模式指定任務內容　　　49
表4-4 語意模式指定任務內容50
表4-5 視覺模式與語意模式評估訪談大綱的差異準則訪談問題　　　54
表4-6 視覺模式與語意模式評估訪談大綱的相關準則訪談問題　　　55
表4-7 視覺模式與語意模式評估訪談大綱的可確知準則訪談問題　　　56
表4-8 視覺模式與語意模式評估訪談大綱的長久準則訪談問題　　　56
表5-1 視覺表徵深度學習模型評估結果　　　60
表5-2 語意表徵深度學習模型評估結果　　　61
表5-3 視覺模式分群驗證實驗結果　　　65
表5-4 語意模式分群驗證實驗結果　　　68
表5-5 專家評估實驗參與者簡介　　　69

圖次
圖2-1 迷因現象的演化過程　　　8
圖2-2 卷積神經網路分析圖片流程示意圖　　　11
圖2-3 K 平均法分群演算法　　　14
圖3-1 MEME-PAM 系統架構圖　　　18
圖3-2 未含有人物臉部資訊的迷因圖片前處理示意圖　　　23
圖3-3 迷因圖片文字敘述處理前後效果之示意圖　　　24
圖3-4 內含文字的迷因圖片　　　26
圖3-5 mixOCR 光學字元識別處理過程示意圖　　　26
圖3-6 分群結果散布圖示意圖　　　29
圖3-7 模式探索模組首頁　　　30
圖3-8 視覺模式之分群結果頁面　　　32
圖3-9 語意模式之分群結果頁面　　　32
圖3-10 視覺模式之模式列表頁面　　　33
圖3-11 語意模式之模式列表頁面　　　34
圖3-12 視覺模式之單一模式頁面　　　35
圖3-13 語意模式之單一模式頁面　　　35
圖3-14 原始貼文頁面　　　36
圖4-1 視覺表徵評估資料集舉例　　　40
圖4-2 視覺表徵深度學習模型評估之執行過程　　　41
圖4-3 迷因圖片的文本使用精靈寶可夢主角名字　　　43
圖4-4 語意表徵深度學習模型評估之執行過程　　　45
圖4-5 專家評估實驗流程　　　47
圖5-1 視覺模式評估指標之Calinski-Harabasz 指標分群驗證結果折線圖　　　63
圖5-2 視覺模式評估指標之Silhouette Coefficient 指標分群驗證結果折線圖　　　63
圖5-3 視覺模式評估指標之Davies-Bouldin 指標分群驗證結果折線圖　　　64
圖5-4 語意模式評估指標之Calinski-Harabasz 指標分群驗證結果折線圖　　　66
圖5-5 語意模式評估指標之Silhouette Coefficient 指標分群驗證結果折線圖　　　67
圖5-6 語意模式評估指標之Davies-Bouldin 指標分群驗證結果折線圖　　　67
圖5-7 專家指出容易判斷出主題的視覺模式　　　71
圖5-8 專家指出難以描述視覺模式之間的差異　　　71
圖5-9 專家指出視覺模式歸納出貓與狗的迷因圖片　　　71
圖5-10 專家指出視覺模式歸納為柴犬的迷因圖片　　　72
圖5-11 專家指出演算法在模式16 歸納錯誤的迷因圖片　　　72
圖5-12 專家認為演算法應將模式16 歸納錯誤的迷因圖片歸納至模式15　　　73
圖5-13 專家指出以四格漫畫為主題的視覺模式　　　76
圖5-14 專家指出以人物為主題的視覺模式　　　77
圖5-15 專家指出兩個具有相似意義的視覺模式　　　78
圖5-16 專家指出迷因圖片中包含酒精相關字詞的語意模式　　　81
圖5-17 專家指出迷因圖片中包含常見詞彙的語意模式　　　81
圖5-18 專家指出本人想了解迷因圖片中的文字敘述的含意　　　83
圖5-19 專家指出本人認為難以解讀的語意模式　　　83
圖5-20 以同樣文字和圖片組成的語意模式　　　87
圖5-21 迷因圖片之原始貼文　　　89
圖5-22 MEME 梗圖倉庫的迷因圖片之主題主要由創作者自行分類　　　93

Álvarez, A. (2004). Memetics: An Evolutionary Theory of Cultural Transmission. Sorites, 15, 24–28.
Alzu’bi, A., Bani Younis, L., Abuarqoub, A., & Hammoudeh, M. (2023). Multimodal Deep Learning with Discriminant Descriptors for Offensive Memes Detection. Journal of Data and Information Quality, 15(3). Scopus. https://doi.org/10.1145/3597308
Amra And Elma LLC. (2022, April 27). TOP HASHTAG FACTS AND STATISTICS IN 2023. Amra & Elma. https://www.amraandelma.com/top-hashtag-facts-and-statistics/
Ankerst, M., Breunig, M. M., Kriegel, H.-P., & Sander, J. (1999). OPTICS: Ordering points to identify the clustering structure. ACM SIGMOD Record, 28(2), 49–60. https://doi.org/10.1145/304181.304187
Asla, N., Kha, I. U., Albahussai, T. I., Almous, N. F., Alolaya, M. O., Almous, S. A., & Alwheb, M. E. (2022). MEDeep: A Deep Learning Based Model for Memotion Analysis. Mathematical Modelling of Engineering Problems, 9(2), 533–538. Scopus. https://doi.org/10.18280/mmep.090232
Babbie, E. R. (2021). The practice of social research (Fifteenth edition). Cengage.
Blackmore, S. (2000). The Power of Memes. Scientific American, 283, 64–66, 68. https://doi.org/10.1038/scientificamerican1000-64
Caliński, T., & Harabasz, J. (1974). A dendrite method for cluster analysis. Communications in Statistics, 3(1), 1–27. https://doi.org/10.1080/03610927408827101
Castaño Díaz, C. M. (2013). Defining and characterizing the concept of Internet Meme. Revista CES Psicología, 6, 82–104.
Chauhan, N. K., & Singh, K. (2018). A Review on Conventional Machine Learning vs Deep Learning. 2018 International Conference on Computing, Power and Communication Technologies (GUCON), 347–352. https://doi.org/10.1109/GUCON.2018.8675097
Danung, J., & Attaway, L. H. (2008). All your media are belong to us: An analysis of the cultural connotations of the internet meme. Literature, Culture and Digital Media, 17.
Davies, D. L., & Bouldin, D. W. (1979). A Cluster Separation Measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1(2), 224–227. https://doi.org/10.1109/TPAMI.1979.4766909
Davis, N. (2017). The Selfish Gene (First edition). Taylor and Francis. https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=1551982
Dawkins, R. (1976). The selfish gene. Oxford University Press. http://www.gbv.de/dms/bowker/toc/9780198575191.pdf
Dawkins, R. (2016). The selfish gene (40th anniversary edition). Oxford University Press. https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=1243961
de Saint Laurent, C., Glăveanu, V. P., & Literat, I. (2021). Internet Memes as Partial Stories: Identifying Political Narratives in Coronavirus Memes. Social Media and Society, 7(1). Scopus. https://doi.org/10.1177/2056305121988932
Docker Inc. (2021, November 11). What is a Container? | Docker. https://www.docker.com/resources/what-container/
Dong, G., & Liu, H. (Eds.). (2018). Feature Engineering for Machine Learning and Data Analytics (First edition). Taylor and Francis. http://public.ebookcentral.proquest.com/choice/publicfullrecord.aspx?p=5322971
Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Kdd, 96(34), 226–231. https://cdn.aaai.org/KDD/1996/KDD96-037.pdf
Fafowora, B. L., & Salaudeen, M. A. (2022). Nigerians and COVID-19 humour: Discursivity and public engagement through pandemic internet memes. Journal of African Media Studies, 14(2), 273–293. Scopus. https://doi.org/10.1386/jams_00078_1
Fischer, D. (2021, July 5). Smartcrop · PyPI. https://pypi.org/project/smartcrop/
Fournier-Viger, P., Gan, W., Wu, Y., Nouioua, M., Song, W., Truong, T., & Duong, H. (2022). Pattern Mining: Current Challenges and Opportunities. In U. K. Rage, V. Goyal, & P. K. Reddy (Eds.), Database Systems for Advanced Applications. DASFAA 2022 International Workshops (pp. 34–49). Springer International Publishing. https://doi.org/10.1007/978-3-031-11217-1_3
Giunchiglia, F., & Bagchi, M. (2021). Object recognition as classification via visual properties. arXiv Preprint arXiv:2112.10531. https://arxiv.org/abs/2112.10531
Gleeson, J. P., O’Sullivan, K. P., Baños, R. A., & Moreno, Y. (2016). Effects of Network Structure, Competition and Memory Time on Social Spreading Phenomena. Physical Review X, 6(2), 021019. https://doi.org/10.1103/PhysRevX.6.021019
Google. (2023, December 15). Tesseract OCR. https://github.com/tesseract-ocr/tesseract
Guo, X., Ma, J., & Zubiaga, A. (2022). Cluster-based deep ensemble learning for emotion classification in Internet memes. Journal of Information Science, 01655515221136241. https://doi.org/10.1177/01655515221136241
Han, J., Kamber, M., & Pei, J. (2011). Data mining: Concepts and techniques. Morgan Kaufmann.
Jin, X., & Han, J. (2017). K-Means Clustering. In C. Sammut & G. I. Webb (Eds.), Encyclopedia of machine learning and data mining. http://dx.doi.org/10.1007/978-1-4899-7687-1
Jupyter. (2023). Project Jupyter. https://jupyter.org/
Kaufman, L. (1990). Partitioning Around Medoids (Program PAM). Finding Groups in Data, 344, 68–125. https://doi.org/10.1002/9780470316801.ch2
Keras Team. (2023). Keras documentation: Keras Applications. Keras. https://keras.io/api/applications/
Kohonen, T. (1982). Analysis of a simple self-organizing process. Biological Cybernetics, 44(2), 135–140. https://doi.org/10.1007/BF00317973
Lankshear, C., & Knobel, M. (2019). Memes, Macros, Meaning, and Menace: Some Trends in Internet Memes. The Journal of Communication and Media Studies, 4(4), 43. https://www.academia.edu/41694045/Memes_Macros_Meaning_and_Menace_Some_Trends_in_Internet_Memes
Lavrač, N., Podpečan, V., & Robnik-Šikonja, M. (2021). Introduction to Representation Learning. In N. Lavrač, V. Podpečan, & M. Robnik-Šikonja (Eds.), Representation Learning: Propositionalization and Embeddings (pp. 1–16). Springer International Publishing. https://doi.org/10.1007/978-3-030-68817-2_1
Leblanc, F. (2022). autocrop: Automatically crops faces from batches of pictures (1.3.0). https://github.com/leblancfg/autocrop
Lin, J. (2020). Meme OCR. https://github.com/johnlinp/meme-ocr
Ling, C., AbuHilal, I., Blackburn, J., De Cristofaro, E., Zannettou, S., & Stringhini, G. (2021). Dissecting the Meme Magic: Understanding Indicators of Virality in Image Memes. Proceedings of the ACM on Human-Computer Interaction, 5(CSCW1), 81:1-81:24. https://doi.org/10.1145/3449155
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A ConvNet for the 2020s (arXiv:2201.03545). arXiv. https://doi.org/10.48550/arXiv.2201.03545
Lonnberg, A., Xiao, P., & Wolfinger, K. (2020). The growth, spread, and mutation of internet phenomena: A study of memes. Results in Applied Mathematics, 6, 100092. https://doi.org/10.1016/j.rinam.2020.100092
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1(14), 281–297. https://www.google.com/books?hl=zh-TW&lr=&id=IC4Ku_7dBFUC&oi=fnd&pg=PA281&dq=macqueen+1967+k+means&ots=nQSgF1HdpP&sig=d-uwxNL9db_3jUqsXPhgt4cR6O8
Madalli, D. P., Balaji, B. P., & Sarangi, A. A. K. (2015). Faceted Ontological Representation for a Music Domain. KNOWLEDGE ORGANIZATION, 42(1), 9–25. https://doi.org/10.5771/0943-7444-2015-1-9
Martínez-Rolán, X., & Piñeiro-Otero, T. (2016). The use of memes in the discourse of political parties on Twitter: Analysing the 2015 state of the nation debate. Communication & Society, 29(1), 145–159.
Meng, X.-L., & Van Dyk, D. (1997). The EM algorithm—An old folk-song sung to a fast new tune. Journal of the Royal Statistical Society Series B: Statistical Methodology, 59(3), 511–567. https://academic.oup.com/jrsssb/article-abstract/59/3/511/7083070
Min, E., Guo, X., Liu, Q., Zhang, G., Cui, J., & Long, J. (2018). A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture. IEEE Access, 6, 39501–39514. https://doi.org/10.1109/ACCESS.2018.2855437
Murel, J., & Kavlakoglu, E. (2024, February 12). What is transfer learning? IBM. https://www.ibm.com/topics/transfer-learning
Nugraha, A. (2015). FENOMENA MEME DI MEDIA SOSIAL (STUDI ETNOGRAFI VIRTUAL POSTING MEME PADA PENGGUNA MEDIA SOSIAL INSTAGRAM). Jurnal Sosioteknologi, 14(3), Article 3. https://doi.org/10.5614/sostek.itbj.2015.14.3.3
Onielfa, C., Casacuberta, C., & Escalera, S. (2022). Influence in Social Networks Through Visual Analysis of Image Memes. Artificial Intelligence Research and Development, 71–80. https://doi.org/10.3233/FAIA220317
Pishghadam, R., Ebrahimi, S., & Derakhshan, A. (2020). Cultuling analysis: A new methodology for discovering cultural memes. International Journal of Society, Culture & Language, 8(2), 17–34.
Python Software Foundation. (2023). BeginnersGuide/Overview—Python Wiki. https://wiki.python.org/moin/BeginnersGuide/Overview
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020). Pre-trained Models for Natural Language Processing: A Survey. Science China Technological Sciences, 63(10), 1872–1897. https://doi.org/10.1007/s11431-020-1647-3
Raath, S. (2023, March 13). How Has Twitter Changed in 2023: The Twitterverse in Numbers | ExpressVPN Blog. ExpressVPN Blog. https://www.expressvpn.com/blog/twitter-in-numbers/
Ramachandran, R., Rajeev, D., Krishnan, S., & Subathra, P. (2015). Deep learning – An overview. International Journal of Applied Engineering Research. https://www.semanticscholar.org/paper/Deep-learning-%E2%80%93-An-overview-Ramachandran-Rajeev/6642890fef3018dd12624459bed780343c3f9d3f
Ranganathan, S. R. (1937). Prolegomena to library classification. Madras Library Association ; E. Goldston.
Reimers, N. (2022). Pretrained Models. Sentence-Transformers Documentation. https://www.sbert.net/docs/pretrained_models.html
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (arXiv:1908.10084). arXiv. https://doi.org/10.48550/arXiv.1908.10084
Rotanova, M. B., & Fedorova, M. V. (2019). Internet meme as the Cyber Laughter Culture Phenomenon in Modern Russian Digital Society. 2019 Communication Strategies in Digital Society Workshop (ComSDS), 65–69. https://doi.org/10.1109/COMSDS.2019.8709650
Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65. https://doi.org/10.1016/0377-0427(87)90125-7
Sammut, C., & Webb, G. I. (2017). Encyclopedia of machine learning and data mining. http://dx.doi.org/10.1007/978-1-4899-7687-1
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2020). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter (arXiv:1910.01108). arXiv. https://doi.org/10.48550/arXiv.1910.01108
SBERT. (2023). Pretrained Models—Sentence Transformers documentation. SBERT.Net. https://sbert.net/docs/sentence_transformer/pretrained_models.html
Semiocast. (2024, July 13). Semiocast—Top languages on Twitter-stats 2024. Semiocast. https://semiocast.com/top-languages-on-twitter-stats/
Sethi, A., Kuchhal, U., Anjum, & Katarya, R. (2021). Study of Various Techniques for the Classification of Hateful Memes. 675–680. Scopus. https://doi.org/10.1109/RTEICT52294.2021.9573926
Sheikholeslami, G., Chatterjee, S., & Zhang, A. (1998). Wavecluster: A multi-resolution clustering approach for very large spatial databases. VLDB, 98, 428–439. http://webdocs.cs.ualberta.ca/~zaiane/courses/cmput695-00/papers/vldb98.pdf
Shifman, L. (2013). Memes in a Digital World: Reconciling with a Conceptual Troublemaker. Journal of Computer-Mediated Communication, 18(3), 362–377. https://doi.org/10.1111/jcc4.12013
Shifman, L. (2014). The Cultural Logic of Photo-Based Meme Genres. Journal of Visual Culture, 13(3), 340–358. https://doi.org/10.1177/1470412914546577
Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition (arXiv:1409.1556). arXiv. https://doi.org/10.48550/arXiv.1409.1556
Skórka, P., Grzywacz, B., Moroń, D., & Lenda, M. (2022). COVID-19 in Memes: The Adaptive Response of Societies to the Pandemic? International Journal of Environmental Research and Public Health, 19(19). Scopus. https://doi.org/10.3390/ijerph191912969
Smith, C. A. (2023). One Does Not Simply Teach Idioms: Meme Creation as Innovative Practice for Virtual EFL Learners. RELC Journal, 54(3), 714–728. https://doi.org/10.1177/00336882211044878
Statista. (2023). X/Twitter: Global audience 2023. Statista. https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selected-countries/
Tan, M., & Le, Q. V. (2021). EfficientNetV2: Smaller Models and Faster Training (arXiv:2104.00298). arXiv. https://doi.org/10.48550/arXiv.2104.00298
Tashpulatova, M., Khalikova, L., Rakhmanova, Y., & Ataeva, G. (2022). Analysis of Students’ Memes: An Integrative Review of the Role of Cultural, Semiotic and Community Memory Paratexts in Multimodal Education. Multidisciplinary International Journal of Research Lines and Projects, 13, 27–34.
Wang, L., & Wood, B. C. (2011). An epidemiological approach to model the viral propagation of memes. Applied Mathematical Modelling, 35(11), 5442–5447. https://doi.org/10.1016/j.apm.2011.04.035
Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., & Zhou, M. (2020). MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. Advances in Neural Information Processing Systems, 33, 5776–5788. https://proceedings.neurips.cc/paper/2020/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
Wang, W., Yang, J., & Muntz, R. (1997). STING: A statistical information grid approach to spatial data mining. Vldb, 97, 186–195. http://cs.bme.hu/~marti/adatbanya/STING.pdf
Wang, X., & Xu, Y. (2019). An improved index for clustering validation based on Silhouette index and Calinski-Harabasz index. IOP Conference Series: Materials Science and Engineering, 569(5), 052024. https://doi.org/10.1088/1757-899X/569/5/052024
Wiggins, B. E., & Bowers, G. B. (2015). Memes as genre: A structurational analysis of the memescape. New Media & Society, 17(11), 1886–1906.
Wu, P. Y., & Mebane Jr, W. R. (2021). MARMOT: A Deep Learning Framework for Constructing Multimodal Representations for Vision-and-Language Tasks (arXiv:2109.11526). arXiv. https://doi.org/10.48550/arXiv.2109.11526
Zheng, A. (2018). Feature engineering for machine learning: Principles and techniques for data scientists (A. Casari; First edition.). O’Reilly Media, Inc.
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021). A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE, 109(1), 43–76. https://doi.org/10.1109/JPROC.2020.3004555